Small life hack: use agent hooks and pre-commit managers like nano-staged to run linters and safeguards. It's far more reliable and faster than asking an agent in 'AGENTS.md'.
5 minutes of setup can mean a tighter loop and fewer tokens. Here's how: evilmartians.com/chronicles/s...
Move LLM safeguards out of AGENTS.md: how agent hooks plus nano-staged run linters on changed files only, cut tokens, and tighten the agent's feedback loop